Real-Time Laryngeal Cancer Boundaries Delineation on White Light and Narrow-Band Imaging Laryngoscopy with Deep Learning
© 2024 The Authors. The Laryngoscope published by Wiley Periodicals LLC on behalf of The American Laryngological, Rhinological and Otological Society, Inc..
OBJECTIVE: To investigate the potential of deep learning for automatically delineating (segmenting) laryngeal cancer superficial extent on endoscopic images and videos.
METHODS: A retrospective study was conducted extracting and annotating white light (WL) and Narrow-Band Imaging (NBI) frames to train a segmentation model (SegMENT-Plus). Two external datasets were used for validation. The model's performances were compared with those of two otolaryngology residents. In addition, the model was tested on real intraoperative laryngoscopy videos.
RESULTS: A total of 3933 images of laryngeal cancer from 557 patients were used. The model achieved the following median values (interquartile range): Dice Similarity Coefficient (DSC) = 0.83 (0.70-0.90), Intersection over Union (IoU) = 0.83 (0.73-0.90), Accuracy = 0.97 (0.95-0.99), Inference Speed = 25.6 (25.1-26.1) frames per second. The external testing cohorts comprised 156 and 200 images. SegMENT-Plus performed similarly on all three datasets for DSC (p = 0.05) and IoU (p = 0.07). No significant differences were noticed when separately analyzing WL and NBI test images on DSC (p = 0.06) and IoU (p = 0.78) and when analyzing the model versus the two residents on DSC (p = 0.06) and IoU (Senior vs. SegMENT-Plus, p = 0.13; Junior vs. SegMENT-Plus, p = 1.00). The model was then tested on real intraoperative laryngoscopy videos.
CONCLUSION: SegMENT-Plus can accurately delineate laryngeal cancer boundaries in endoscopic images, with performances equal to those of two otolaryngology residents. The results on the two external datasets demonstrate excellent generalization capabilities. The computation speed of the model allowed its application on videolaryngoscopies simulating real-time use. Clinical trials are needed to evaluate the role of this technology in surgical practice and resection margin improvement.
LEVEL OF EVIDENCE: III Laryngoscope, 2024.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - year:2024 |
|---|---|
| Enthalten in: |
The Laryngoscope - (2024) vom: 04. Jan. |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Sampieri, Claudio [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Artificial intelligence |
|---|
| Anmerkungen: |
Date Revised 04.01.2024 published: Print-Electronic Citation Status Publisher |
|---|
| doi: |
10.1002/lary.31255 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM366653946 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM366653946 | ||
| 003 | DE-627 | ||
| 005 | 20240108141955.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240108s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1002/lary.31255 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1248.xml |
| 035 | |a (DE-627)NLM366653946 | ||
| 035 | |a (NLM)38174772 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Sampieri, Claudio |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Real-Time Laryngeal Cancer Boundaries Delineation on White Light and Narrow-Band Imaging Laryngoscopy with Deep Learning |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 04.01.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status Publisher | ||
| 520 | |a © 2024 The Authors. The Laryngoscope published by Wiley Periodicals LLC on behalf of The American Laryngological, Rhinological and Otological Society, Inc. | ||
| 520 | |a OBJECTIVE: To investigate the potential of deep learning for automatically delineating (segmenting) laryngeal cancer superficial extent on endoscopic images and videos | ||
| 520 | |a METHODS: A retrospective study was conducted extracting and annotating white light (WL) and Narrow-Band Imaging (NBI) frames to train a segmentation model (SegMENT-Plus). Two external datasets were used for validation. The model's performances were compared with those of two otolaryngology residents. In addition, the model was tested on real intraoperative laryngoscopy videos | ||
| 520 | |a RESULTS: A total of 3933 images of laryngeal cancer from 557 patients were used. The model achieved the following median values (interquartile range): Dice Similarity Coefficient (DSC) = 0.83 (0.70-0.90), Intersection over Union (IoU) = 0.83 (0.73-0.90), Accuracy = 0.97 (0.95-0.99), Inference Speed = 25.6 (25.1-26.1) frames per second. The external testing cohorts comprised 156 and 200 images. SegMENT-Plus performed similarly on all three datasets for DSC (p = 0.05) and IoU (p = 0.07). No significant differences were noticed when separately analyzing WL and NBI test images on DSC (p = 0.06) and IoU (p = 0.78) and when analyzing the model versus the two residents on DSC (p = 0.06) and IoU (Senior vs. SegMENT-Plus, p = 0.13; Junior vs. SegMENT-Plus, p = 1.00). The model was then tested on real intraoperative laryngoscopy videos | ||
| 520 | |a CONCLUSION: SegMENT-Plus can accurately delineate laryngeal cancer boundaries in endoscopic images, with performances equal to those of two otolaryngology residents. The results on the two external datasets demonstrate excellent generalization capabilities. The computation speed of the model allowed its application on videolaryngoscopies simulating real-time use. Clinical trials are needed to evaluate the role of this technology in surgical practice and resection margin improvement | ||
| 520 | |a LEVEL OF EVIDENCE: III Laryngoscope, 2024 | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a artificial intelligence | |
| 650 | 4 | |a laryngeal cancer | |
| 650 | 4 | |a laryngoscopy | |
| 650 | 4 | |a narrow-band imaging | |
| 650 | 4 | |a segmentation | |
| 650 | 4 | |a white light imaging | |
| 700 | 1 | |a Azam, Muhammad Adeel |e verfasserin |4 aut | |
| 700 | 1 | |a Ioppi, Alessandro |e verfasserin |4 aut | |
| 700 | 1 | |a Baldini, Chiara |e verfasserin |4 aut | |
| 700 | 1 | |a Moccia, Sara |e verfasserin |4 aut | |
| 700 | 1 | |a Kim, Dahee |e verfasserin |4 aut | |
| 700 | 1 | |a Tirrito, Alessandro |e verfasserin |4 aut | |
| 700 | 1 | |a Paderno, Alberto |e verfasserin |4 aut | |
| 700 | 1 | |a Piazza, Cesare |e verfasserin |4 aut | |
| 700 | 1 | |a Mattos, Leonardo S |e verfasserin |4 aut | |
| 700 | 1 | |a Peretti, Giorgio |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t The Laryngoscope |d 1945 |g (2024) vom: 04. Jan. |w (DE-627)NLM000205370 |x 1531-4995 |7 nnns |
| 773 | 1 | 8 | |g year:2024 |g day:04 |g month:01 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1002/lary.31255 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |j 2024 |b 04 |c 01 | ||